官方文件說明與範例 https://google.github.io/mediapipe/solutions/face_detection.html

以下只是將官方文件範例程式碼加註中文說明

相關參數

Solution APIs

Configuration Options

Naming style and availability may differ slightly across platforms/languages.

MODEL_SELECTION

An integer index 0 or 1. Use 0 to select a short-range model that works best for faces within 2 meters from the camera, and 1 for a full-range model best for faces within 5 meters. For the full-range option, a sparse model is used for its improved inference speed. Please refer to the model cards for details. Default to 0 if not specified.

MIN_DETECTION_CONFIDENCE

Minimum confidence value ([0.0, 1.0]) from the face detection model for the detection to be considered successful. Default to 0.5.

Output

Naming style may differ slightly across platforms/languages.

DETECTIONS

Collection of detected faces, where each face is represented as a detection proto message that contains a bounding box and 6 key points (right eye, left eye, nose tip, mouth center, right ear tragion, and left ear tragion). The bounding box is composed of xmin and width (both normalized to [0.0, 1.0] by the image width) and ymin and height (both normalized to [0.0, 1.0] by the image height). Each key point is composed of x and y, which are normalized to [0.0, 1.0] by the image width and height respectively.

有關Python語言的with用法說明：文字擷取自https://blog.gtwang.org/programming/python-with-context-manager-tutorial/

Python 語言提供了 with 這個獨特的語法，可讓程式設計者更容易管理這些開啟的資源，在這樣的語法架構之下，Python 程式會自動進行資源的建立、清理與回收動作，讓程式設計者在使用各種資源時更為方便 

例如  # 以 with 開啟檔案

with open(filename) as f:

這裡在使用 with 開啟檔案時，會將開啟的檔案一樣放在 f 變數中，但是這個 f 只有在這個 with 的範圍內可以使用，而離開這個範圍時 f 就會自動被關閉，回收相關的資源。 

所以下方的程式碼

with mp_face_detection.FaceDetection(

    model_selection=0, min_detection_confidence=0.5) as face_detection:

當偵測時，把偵測的資料放進face_detection這個變數，當結束偵測時，face_detection就會自動關閉，回收相關的資源

import cv2

import mediapipe as mp

# 匯入cv2與mediapipe，並且命名

# face Detection只是Mediapipe的眾多solutions其中的一個

# 新增物件mp_face_detection,mp_drawing

mp_face_detection = mp.solutions.face_detection

mp_drawing = mp.solutions.drawing_utils

# For webcam input:

# 做影片的擷取，0代表使用webcam

cap = cv2.VideoCapture(0)

# FaceDetection的參數model_selection有0跟1可以選擇，選擇0代表是2公尺以內，如果選擇1代表5公尺以內

# min_detection_confidence通常設0.5，當值到0.5時代表偵測到的是一張人臉

with mp_face_detection.FaceDetection(

    model_selection=0, min_detection_confidence=0.5) as face_detection:

# 以下都是while的語法，當開啟視訊成功時要執行的，如果成功就開始擷取圖片，視訊沒開啟成功就繼續往下執行

# 如果視訊鏡頭故障或其他因素沒有開啟，把continue換成break會中斷程式

  while cap.isOpened():

    success, image = cap.read()

    if not success:

      print("Ignoring empty camera frame.")

      # If loading a video, use 'break' instead of 'continue'.

      continue

    # 水平翻轉影像作加強處理,將BGR 影像轉換為 RGB

    # cv2.flip(image, 1)裡的1帶表對Y軸做旋轉，0是對X軸

    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)

    # 為了增加效能, optionally mark the image as not writeable to

    # pass by reference.

    image.flags.writeable = False

    # face_detection處理結果傳回到results變數

    results = face_detection.process(image)

    # 繪製臉部偵測的註解到影像裡，包含裡面的每一個點跟框

    # 首先要把image改成可寫入

    # 處理完準備輸出前把影像由RGB轉換為BGR

    image.flags.writeable = True

    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)

    # 如果有results的值，就把每個偵測的點描繪上去圖片裡

    if results.detections:

    # 因為有六個點，包括耳朵、眼睛、鼻子跟嘴巴，所以使用for把六個點標註上去

    # 也有其他參數可以改變顏色

      for detection in results.detections:

        mp_drawing.draw_detection(image, detection)

    # 視窗標題MediaPipe Face Detection

    cv2.imshow('MediaPipe Face Detection', image)

    # 如果按ESC就離開

    if cv2.waitKey(5) & 0xFF == 27:

      break

# 釋出webcam使用資源

cap.release()

偵測到人數大於二就變粗框，顏色改為紅色

差異在下面那一段程式碼

        if len(results.detections) > 2: #偵測到的人臉數大於2

            for detection in results.detections:

                mp_drawing.draw_detection(image, detection,

                bbox_drawing_spec=mp_drawing.DrawingSpec(color=(0, 0, 255), thickness=7))

        else:

        # 如果不需要判斷人數大於幾個人的話就從 if ......else:這一段程式碼刪除

完整程式碼

import cv2

import mediapipe as mp

# 匯入cv2與mediapipe，並且命名

# face Detection只是Mediapipe的眾多solutions其中的一個

# 新增物件mp_face_detection,mp_drawing

mp_face_detection = mp.solutions.face_detection

mp_drawing = mp.solutions.drawing_utils

# For webcam input:

# 做影片的擷取，0代表使用webcam

cap = cv2.VideoCapture(0)

# FaceDetection的參數model_selection有0跟1可以選擇，選擇0代表是2公尺以內，如果選擇1代表5公尺以內

# min_detection_confidence通常設0.5，當值到0.5時代表偵測到的是一張人臉

with mp_face_detection.FaceDetection(

    model_selection=0, min_detection_confidence=0.5) as face_detection:

# 以下都是while的語法，當開啟視訊成功時要執行的，如果成功就開始擷取圖片，視訊沒開啟成功就繼續往下執行

# 如果視訊鏡頭故障或其他因素沒有開啟，把continue換成break會中斷程式

  while cap.isOpened():

    success, image = cap.read()

    if not success:

      print("Ignoring empty camera frame.")

      # If loading a video, use 'break' instead of 'continue'.

      continue

    # 水平翻轉影像作加強處理,將BGR 影像轉換為 RGB

    # cv2.flip(image, 1)裡的1帶表對Y軸做旋轉，0是對X軸

    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)

    # 為了增加效能, optionally mark the image as not writeable to

    # pass by reference.

    image.flags.writeable = False

    # face_detection處理結果傳回到results變數

    results = face_detection.process(image)

    # 繪製臉部偵測的註解到影像裡，包含裡面的每一個點跟框

    # 首先要把image改成可寫入

    # 處理完準備輸出前把影像由RGB轉換為BGR

    image.flags.writeable = True

    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)

    # 如果有results的值，就把每個偵測的點描繪上去圖片裡

    if results.detections:

    # 因為有六個點，包括耳朵、眼睛、鼻子跟嘴巴，所以使用for把六個點標註上去

    # 也有其他參數可以改變顏色

        if len(results.detections) > 2: #偵測到的人臉數大於2

            for detection in results.detections:

                mp_drawing.draw_detection(image, detection,

                bbox_drawing_spec=mp_drawing.DrawingSpec(color=(0, 0, 255), thickness=7))

        else:

        # 如果不需要判斷人數大於幾個人的話就從 if ......else:這一段程式碼刪除

            for detection in results.detections:

                mp_drawing.draw_detection(image, detection)

    # 視窗標題MediaPipe Face Detection

    cv2.imshow('MediaPipe Face Detection', image)

    # 如果按ESC就離開

    if cv2.waitKey(5) & 0xFF == 27:

      break

# 釋出webcam使用資源

cap.release()